Microsoft Technology Licensing, LLC

Linkedin Corporation

Ke Wang

Ahmed Hassan Mohamed

Bo Liu

Alex Ching Lai

Songtao Guo

Baoshi Yan

Krishna C Vitaldevara

Xiaolong Li

Zhen Wei

Avrilia Floratou

Ashvin Agrawal

Ram Pratap Singh

Sridhar Raman

Tiancong Zhou

Jagadeesh Kunda

Daniel E Musgrave

Ananth Inamti Sundararaj

Thomas Moscibroda

Marcus Felipe Fontoura

Yimin Deng

Aditya Bhandari

Yong Xie

Sameh Elnikety

Ricardo Gouvêa Bianchini

Chandrasekhar Pasupuleti

Brian Jacob Corell

Inigo Goiri Presa

Aarti Kumar

Christopher Matthew Degiere

Kevin Michael Carter

Song Lin

Honghao Qiu

Chao Chen

Divya Darbari

Gouthami Kamalnath

Rekha Thakur

Kapil Arya

Alper Gun

Lihao Zhang

Keith Wai Kit Tsang

Kushal Manohar Aurangabadkar

Anirudhan Vijayakanthan

Victor Renjie Fu

Pol Llado

Victor Macêdo Alexandrino

User data is extracted from a user data shard and copied into a user-isolated tenant shard. Instructions for accessing the user data are stored in a separate data store. A tenant administrator computing system retrieves and runs the instructions for accessing and exporting the user data from the user-isolated tenant shard.

Exporting customer data using a compliant tenant shard

The present disclosure relates to providing personalized service schedule in a computing network for a service provider to provide a service. In particular, the systems described herein utilize signal history of a plurality of users to train a model and to predict a cumulative signal amount for an individual user for a predetermined time frame in the future by drawing inferences from the model. The system described herein further transforms the predicted cumulative signal amounts to activity data and a personalized service schedule for the individual user may be updated based on the predicted activity data. The personalized service schedule may be utilized by disabling the service, or pausing the service or pausing a feature of the service when the predicted activity data indicates that the user is likely to be inactive.

Personalized service scheduling

The present disclosure describes a type of virtual machine, which the present disclosure may refer to as a harvest virtual machine, that may allow improved utilization of physical computing resources on a cloud-computing system. First, the harvest virtual machine may be evictable. In other words, higher priority virtual machines may preempt the harvest virtual machine's access to physical computing resources. Second, the harvest virtual machine may receive access to a dynamic amount of physical computing resources during the course of its operating life. Third, the harvest virtual machine may have a minimum size (in terms of an amount of physical computing resources) and may terminate whenever the harvest virtual machine has access to an amount of physical computing resources less than the minimum size.

Harvest virtual machine for utilizing cloud-computing resources

Techniques of interaction data processing in a distributed computing system are disclosed herein. One example technique includes upon receiving a user interface output having a content item to be surfaced on a client device and a script configured to detect an interaction with the content item at the client device, surfacing the user interface output having the content item on a display of the client device and automatically executing the script embedded in the user interface output to detect an interaction with the surfaced content item at the client device. Upon detecting an interaction with the content item on the surfaced user interface output, the example technique also includes generating and transmitting interaction data representing the detected interaction to a remote server.

Interaction signal processing in distributed computing systems

A method for signal request caching is described. Signal requests are received at a signal processor from a plurality of computing devices. The received signal requests are routed to a signal data store. An ingestion rate of the received signal requests is monitored by the signal processor. When the ingestion rate meets a signal request rate threshold of the signal data store, overflow signal requests of the received signal requests are automatically routed to an intermediate cache instead of the signal data store. The overflow signal requests within the intermediate cache are aggregated into one or more signal packages, each of the one or more signal packages containing a plurality of overflow signal requests. The one or more signal packages are stored at the signal data store.

Overflow signal caching and aggregation

A system is described herein for mitigating slow process instances in a streaming application. The system includes a slow process instance candidate identifier configured to identify, based on a relative watermark latency, a set of slow process instance candidates from among a plurality of process instances that comprise the streaming application. The system further includes a set of filters configured to remove false positives from the set of slow process instance candidates. The filters account for window operations performed by the process instances as well as stabilization time needed for downstream process instances to stabilize after a slow upstream process instance is mitigated by a mitigation implementer, which may also be included in the system.

Mitigating slow instances in large-scale streaming pipelines

A computing device, including a processor configured to receive a training data set including a first plurality of log entries. Each log entry of the first plurality of log entries may be associated with a tag indicating whether the log entry includes sensitive data. The processor may be further configured to train a sensitivity classification neural network using the training data set. The processor may be further configured to apply the sensitivity classification neural network to a test data set including a second plurality of log entries to obtain a first classified test data set. The processor may be further configured to apply a rule-based data sensitivity classification algorithm to the test data set to obtain a second classified test data set. Based on the first classified test data set and the second classified test data set, the processor may be further configured to modify the sensitivity classification neural network.

Sensitivity classification neural network

A method for managing a mailbox based on user activity comprises receiving output signals from each of a plurality of mailbox workloads. The output signals may be indicative of user activity for each workload. A last user action time may be determined based on the received output signals using pre-determined, workload specific criteria. A pre-determined action may be performed on the mailbox responsive to a lapsed duration from the last user action time increasing above a threshold.

Mailbox management based on user activity

A messaging system configured for recommending messages is provided. The messaging system machine trains a prediction model associated with a user based on past review and response times for past messages. During runtime, the messaging system generates a predicted user action time for each new message based on the prediction model and tags each new message with a corresponding predicted user action time. Based on an amount of available time, the predicted user action time for each new message, and importance for each new message, the messaging system determines a recommended set of new messages that the user should read and respond to during the available time, whereby a sum of the predicted user action time of the recommended set of new messages is equal to or less than the available time. The recommended set of new messages are visually distinguished for the user.

Context and time prediction based message recommendation system

In an example embodiment, a member profile corresponding to a member of a social networking service is obtained. Usage information for the member is then obtained, and one or more member metrics are calculated based on the member profile and usage information for the corresponding member. A plurality of features are extracted from the member profile and the one or more member metrics. The plurality of features is inserted into an organization name confidence score model to obtain a confidence score for an organization name in the member profile.

Inferring attributes of organizations using member graph

In representative embodiments, multiple cloud computing infrastructures, each having its own application and management fabric, coexist with in the same cloud computing infrastructure. This results in a cloud computing infrastructure where multiple management fabrics and application fabrics coexist to offer their own services and cross platform services. Each functions independently and also communicates with each other to offer high availability and disaster recovery. One application and management infrastructure is a host to the other application and management infrastructure. The hosted infrastructure accesses underlying fabrics through the host infrastructure. A resultant system comprises a common hardware fabric, a common runtime, and a service fabric comprising services from both the host and hosted infrastructures.

Multi-service application fabric architecture

Methods, systems and computer program products for identifying a relationship between sub-units of an entity are described. The sub-units are segmented into one or more candidate related groups based on one or more general attributes and a pair of the sub-units of the one or more candidate related sub-units is selected. The pair of sub-units is analyzed to determine a relationship between the sub-units and the relationship between the sub-units is identified based on the determined relationship.

Determining an entity's hierarchical relationship via a social graph

Growing community of inventors

Redmond, WA, United States of America

Ke Wang